DB ssh
SSH server management — connect, configure, deploy, administer Linux servers with safety gates.
SSH server management — connect, configure, deploy, administer Linux servers with safety gates.
As a process B 68/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 6
-
high Exfiltration
exfil-read-secret-filesreferences/docker-auth-flow.md:94Reads credential / secret filesWithout a credential helper/store, Docker keeps base…ded auth in `~/.docker/config.json`; base64 is not encryption. With a helper, secrets are stored by that helper. This JSON is an illustrative
-
high Exfiltration
exfil-read-secret-filesSKILL.md:198Reads credential / secret files> ! ssh-copy-id -i ~/.ssh/id_e…pub -p PORT USER@HOST
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellreferences/safety-rules.md:133Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `curl \| bash` | PRIVILEGE | Arbitrary code execution |
table -
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Agent AskUserQuestion Glob Grep
-
low Dangerous commands
cmd-background-processreferences/safety-rules.md:90Starts a background / autostarted process (documentation table row)| Services | `systemctl enable`, `systemctl disable` | Boot behavior |
table -
low Dangerous commands
cmd-cron-mentionreferences/safety-rules.md:91Mentions editing / listing crontab (documentation table row)| Config | Edit any file in `/etc/`, `crontab -e` | System config |
table
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5109 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5109 tokens
- 85Steps. 5 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 95: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 29 headings
- +3Step-by-step instructions: 5 items
- +3Output format is stated explicitly
- +4Has examples (35 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.